Výsledky vyhledávání

Report

LC-Score: Reference-less estimation of Text Comprehension Difficulty

Autor: Tardy, Paul, Roze, Charlotte, Poupet, Paul

Being able to read and understand written text is critical in a digital era. However, studies shows that a large fraction of the population experiences comprehension issues. In this context, further initiatives in accessibility are required to improv

Externí odkaz: http://arxiv.org/abs/2310.02754

Zobrazit plný text záznamu

Report

Leverage Unlabeled Data for Abstractive Speech Summarization with Self-Supervised Learning and Back-Summarization

Autor: Tardy, Paul, de Seynes, Louis, Hernandez, François, Nguyen, Vincent, Janiszek, David, Estève, Yannick

Supervised approaches for Neural Abstractive Summarization require large annotated corpora that are costly to build. We present a French meeting summarization task where reports are predicted based on the automatic transcription of the meeting audio

Externí odkaz: http://arxiv.org/abs/2007.15296

Zobrazit plný text záznamu

Report

Align then Summarize: Automatic Alignment Methods for Summarization Corpus Creation

Autor: Tardy, Paul, Janiszek, David, Estève, Yannick, Nguyen, Vincent

Publikováno v: LREC 2020 -- Proceedings of The 12th Language Resources and Evaluation Conference, 2020, pp. 6718--6724

Summarizing texts is not a straightforward task. Before even considering text summarization, one should determine what kind of summary is expected. How much should the information be compressed? Is it relevant to reformulate or should the summary sti

Externí odkaz: http://arxiv.org/abs/2007.07841

Zobrazit plný text záznamu

De la tuberculose basale post-pleurétique.

Autor: Tardy, Paul-Edouard.

Th.--Méd.--Lyon, 1913-1914.
Lyon, 1913-1914, n ° 26.

Externí odkaz: http://catalogue.bnf.fr/ark:/12148/cb369344384

Zobrazit plný text záznamu

Approches neuronales pour le résumé abstractif de transcriptions de parole

Autor: Tardy, Paul

Publikováno v: Informatique et langage [cs.CL]. Le Mans Université, 2021. Français

In this thesis, we study the application of Deep Learning Neural Approaches for abstractive summarization for meetings reports generation. This work takes place in a context where Deep Learning is omnipresent in the Natural Language Processing field

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::339feae4e13a8e7c27f2c6fc6eb66172
https://tel.archives-ouvertes.fr/tel-03259468/file/MANUSCRIPT_pltrdy_20210531.pdf

Zobrazit plný text záznamu